IR: Add COMDATs to the IR

This new IR facility allows us to represent the object-file semantic of
a COMDAT group.

COMDATs allow us to tie together sections and make the inclusion of one
dependent on another. This is required to implement features like MS
ABI VFTables and optimizing away certain kinds of initialization in C++.

This functionality is only representable in COFF and ELF, Mach-O has no
similar mechanism.

Differential Revision: http://reviews.llvm.org/D4178

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211920 91177308-0d34-0410-b5e6-96231b3b80d8

7 files changed, 148 insertions, 9 deletions

diff --git a/lib/IR/AsmWriter.cpp b/lib/IR/AsmWriter.cpp
index 398e3d5f2a..87d26b164b 100644
--- a/lib/IR/AsmWriter.cpp
+++ b/lib/IR/AsmWriter.cpp
@@ -106,6 +106,7 @@ static void PrintEscapedString(StringRef Name, raw_ostream &Out) {
 
 enum PrefixType {
   GlobalPrefix,
+  ComdatPrefix,
   LabelPrefix,
   LocalPrefix,
   NoPrefix
@@ -119,6 +120,7 @@ static void PrintLLVMName(raw_ostream &OS, StringRef Name, PrefixType Prefix) {
   switch (Prefix) {
   case NoPrefix: break;
   case GlobalPrefix: OS << '@'; break;
+  case ComdatPrefix: OS << '$'; break;
   case LabelPrefix:  break;
   case LocalPrefix:  OS << '%'; break;
   }
@@ -1165,8 +1167,15 @@ static void WriteAsOperandInternal(raw_ostream &Out, const Value *V,
 }
 
 void AssemblyWriter::init() {
-  if (TheModule)
-    TypePrinter.incorporateTypes(*TheModule);
+  if (!TheModule)
+    return;
+  TypePrinter.incorporateTypes(*TheModule);
+  for (const Function &F : *TheModule)
+    if (const Comdat *C = F.getComdat())
+      Comdats.insert(C);
+  for (const GlobalVariable &GV : TheModule->globals())
+    if (const Comdat *C = GV.getComdat())
+      Comdats.insert(C);
 }
 
 
@@ -1308,6 +1317,15 @@ void AssemblyWriter::printModule(const Module *M) {
 
   printTypeIdentities();
 
+  // Output all comdats.
+  if (!Comdats.empty())
+    Out << '\n';
+  for (const Comdat *C : Comdats) {
+    printComdat(C);
+    if (C != Comdats.back())
+      Out << '\n';
+  }
+
   // Output all globals.
   if (!M->global_empty()) Out << '\n';
   for (Module::const_global_iterator I = M->global_begin(), E = M->global_end();
@@ -1470,6 +1488,10 @@ void AssemblyWriter::printGlobal(const GlobalVariable *GV) {
     PrintEscapedString(GV->getSection(), Out);
     Out << '"';
   }
+  if (GV->hasComdat()) {
+    Out << ", comdat ";
+    PrintLLVMName(Out, GV->getComdat()->getName(), ComdatPrefix);
+  }
   if (GV->getAlignment())
     Out << ", align " << GV->getAlignment();
 
@@ -1506,10 +1528,19 @@ void AssemblyWriter::printAlias(const GlobalAlias *GA) {
     writeOperand(Aliasee, !isa<ConstantExpr>(Aliasee));
   }
 
+  if (GA->hasComdat()) {
+    Out << ", comdat ";
+    PrintLLVMName(Out, GA->getComdat()->getName(), ComdatPrefix);
+  }
+
   printInfoComment(*GA);
   Out << '\n';
 }
 
+void AssemblyWriter::printComdat(const Comdat *C) {
+  C->print(Out);
+}
+
 void AssemblyWriter::printTypeIdentities() {
   if (TypePrinter.NumberedTypes.empty() &&
       TypePrinter.NamedTypes.empty())
@@ -1647,6 +1678,10 @@ void AssemblyWriter::printFunction(const Function *F) {
     PrintEscapedString(F->getSection(), Out);
     Out << '"';
   }
+  if (F->hasComdat()) {
+    Out << " comdat ";
+    PrintLLVMName(Out, F->getComdat()->getName(), ComdatPrefix);
+  }
   if (F->getAlignment())
     Out << " align " << F->getAlignment();
   if (F->hasGC())
@@ -2158,6 +2193,31 @@ void NamedMDNode::print(raw_ostream &ROS) const {
   W.printNamedMDNode(this);
 }
 
+void Comdat::print(raw_ostream &ROS) const {
+  PrintLLVMName(ROS, getName(), ComdatPrefix);
+  ROS << " = comdat ";
+
+  switch (getSelectionKind()) {
+  case Comdat::Any:
+    ROS << "any";
+    break;
+  case Comdat::ExactMatch:
+    ROS << "exactmatch";
+    break;
+  case Comdat::Largest:
+    ROS << "largest";
+    break;
+  case Comdat::NoDuplicates:
+    ROS << "noduplicates";
+    break;
+  case Comdat::SameSize:
+    ROS << "samesize";
+    break;
+  }
+
+  ROS << '\n';
+}
+
 void Type::print(raw_ostream &OS) const {
   TypePrinting TP;
   TP.print(const_cast<Type*>(this), OS);
@@ -2241,5 +2301,8 @@ void Type::dump() const { print(dbgs()); }
 // Module::dump() - Allow printing of Modules from the debugger.
 void Module::dump() const { print(dbgs(), nullptr); }
 
+// \brief Allow printing of Comdats from the debugger.
+void Comdat::dump() const { print(dbgs()); }
+
 // NamedMDNode::dump() - Allow printing of NamedMDNodes from the debugger.
 void NamedMDNode::dump() const { print(dbgs()); }
diff --git a/lib/IR/AsmWriter.h b/lib/IR/AsmWriter.h
index b4ce6de10d..aef9c8a3e9 100644
--- a/lib/IR/AsmWriter.h
+++ b/lib/IR/AsmWriter.h
@@ -16,6 +16,7 @@
 #define LLVM_IR_ASSEMBLYWRITER_H
 
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SetVector.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/TypeFinder.h"
@@ -26,6 +27,7 @@ namespace llvm {
 class BasicBlock;
 class Function;
 class GlobalValue;
+class Comdat;
 class Module;
 class NamedMDNode;
 class Value;
@@ -70,6 +72,7 @@ private:
   SlotTracker &Machine;
   TypePrinting TypePrinter;
   AssemblyAnnotationWriter *AnnotationWriter;
+  SetVector<const Comdat *> Comdats;
 
 public:
   /// Construct an AssemblyWriter with an external SlotTracker
@@ -101,6 +104,7 @@ public:
   void printTypeIdentities();
   void printGlobal(const GlobalVariable *GV);
   void printAlias(const GlobalAlias *GV);
+  void printComdat(const Comdat *C);
   void printFunction(const Function *F);
   void printArgument(const Argument *FA, AttributeSet Attrs, unsigned Idx);
   void printBasicBlock(const BasicBlock *BB);
diff --git a/lib/IR/CMakeLists.txt b/lib/IR/CMakeLists.txt
index b027ae5f50..38a80b18bd 100644
--- a/lib/IR/CMakeLists.txt
+++ b/lib/IR/CMakeLists.txt
@@ -3,6 +3,7 @@ add_llvm_library(LLVMCore
   Attributes.cpp
   AutoUpgrade.cpp
   BasicBlock.cpp
+  Comdat.cpp
   ConstantFold.cpp
   ConstantRange.cpp
   Constants.cpp
diff --git a/lib/IR/Comdat.cpp b/lib/IR/Comdat.cpp
new file mode 100644
index 0000000000..80715ff40b
--- /dev/null
+++ b/lib/IR/Comdat.cpp
@@ -0,0 +1,25 @@
+//===-- Comdat.cpp - Implement Metadata classes --------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the Comdat class.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/IR/Comdat.h"
+#include "llvm/ADT/StringMap.h"
+using namespace llvm;
+
+Comdat::Comdat(SelectionKind SK, StringMapEntry<Comdat> *Name)
+    : Name(Name), SK(SK) {}
+
+Comdat::Comdat(Comdat &&C) : Name(C.Name), SK(C.SK) {}
+
+Comdat::Comdat() : Name(nullptr), SK(Comdat::Any) {}
+
+StringRef Comdat::getName() const { return Name->first(); }
diff --git a/lib/IR/Globals.cpp b/lib/IR/Globals.cpp
index 5410cc031d..244e3e4bae 100644
--- a/lib/IR/Globals.cpp
+++ b/lib/IR/Globals.cpp
@@ -59,15 +59,10 @@ void GlobalValue::copyAttributesFrom(const GlobalValue *Src) {
   setDLLStorageClass(Src->getDLLStorageClass());
 }
 
-static const GlobalObject *getBaseObject(const Constant &C) {
-  // FIXME: We should probably return a base + offset pair for non-zero GEPs.
-  return dyn_cast<GlobalObject>(C.stripPointerCasts());
-}
-
 unsigned GlobalValue::getAlignment() const {
   if (auto *GA = dyn_cast<GlobalAlias>(this)) {
     // In general we cannot compute this at the IR level, but we try.
-    if (const GlobalObject *GO = getBaseObject(*GA->getAliasee()))
+    if (const GlobalObject *GO = GA->getBaseObject())
       return GO->getAlignment();
 
     // FIXME: we should also be able to handle:
@@ -96,13 +91,23 @@ void GlobalObject::copyAttributesFrom(const GlobalValue *Src) {
 const char *GlobalValue::getSection() const {
   if (auto *GA = dyn_cast<GlobalAlias>(this)) {
     // In general we cannot compute this at the IR level, but we try.
-    if (const GlobalObject *GO = getBaseObject(*GA->getAliasee()))
+    if (const GlobalObject *GO = GA->getBaseObject())
       return GO->getSection();
     return "";
   }
   return cast<GlobalObject>(this)->getSection();
 }
 
+Comdat *GlobalValue::getComdat() {
+  if (auto *GA = dyn_cast<GlobalAlias>(this)) {
+    // In general we cannot compute this at the IR level, but we try.
+    if (const GlobalObject *GO = GA->getBaseObject())
+      return const_cast<GlobalObject *>(GO)->getComdat();
+    return nullptr;
+  }
+  return cast<GlobalObject>(this)->getComdat();
+}
+
 void GlobalObject::setSection(StringRef S) { Section = S; }
 
 bool GlobalValue::isDeclaration() const {
diff --git a/lib/IR/Module.cpp b/lib/IR/Module.cpp
index 9889f00974..d853bf4cfa 100644
--- a/lib/IR/Module.cpp
+++ b/lib/IR/Module.cpp
@@ -453,3 +453,11 @@ unsigned Module::getDwarfVersion() const {
     return dwarf::DWARF_VERSION;
   return cast<ConstantInt>(Val)->getZExtValue();
 }
+
+Comdat *Module::getOrInsertComdat(StringRef Name) {
+  Comdat C;
+  StringMapEntry<Comdat> &Entry =
+      ComdatSymTab.GetOrCreateValue(Name, std::move(C));
+  Entry.second.Name = &Entry;
+  return &Entry.second;
+}
diff --git a/lib/IR/Verifier.cpp b/lib/IR/Verifier.cpp
index ad3c29c564..24f3acb995 100644
--- a/lib/IR/Verifier.cpp
+++ b/lib/IR/Verifier.cpp
@@ -107,6 +107,12 @@ struct VerifierSupport {
     OS << ' ' << *T;
   }
 
+  void WriteComdat(const Comdat *C) {
+    if (!C)
+      return;
+    OS << *C;
+  }
+
   // CheckFailed - A check failed, so print out the condition and the message
   // that failed.  This provides a nice place to put a breakpoint if you want
   // to see why something is not correct.
@@ -138,6 +144,12 @@ struct VerifierSupport {
     WriteType(T3);
     Broken = true;
   }
+
+  void CheckFailed(const Twine &Message, const Comdat *C) {
+    OS << Message.str() << "\n";
+    WriteComdat(C);
+    Broken = true;
+  }
 };
 class Verifier : public InstVisitor<Verifier>, VerifierSupport {
   friend class InstVisitor<Verifier>;
@@ -230,6 +242,9 @@ public:
          I != E; ++I)
       visitNamedMDNode(*I);
 
+    for (const StringMapEntry<Comdat> &SMEC : M.getComdatSymbolTable())
+      visitComdat(SMEC.getValue());
+
     visitModuleFlags(M);
     visitModuleIdents(M);
 
@@ -246,6 +261,7 @@ private:
                            const GlobalAlias &A, const Constant &C);
   void visitNamedMDNode(const NamedMDNode &NMD);
   void visitMDNode(MDNode &MD, Function *F);
+  void visitComdat(const Comdat &C);
   void visitModuleIdents(const Module &M);
   void visitModuleFlags(const Module &M);
   void visitModuleFlag(const MDNode *Op,
@@ -387,6 +403,7 @@ void Verifier::visitGlobalVariable(const GlobalVariable &GV) {
               "'common' global must have a zero initializer!", &GV);
       Assert1(!GV.isConstant(), "'common' global may not be marked constant!",
               &GV);
+      Assert1(!GV.hasComdat(), "'common' global may not be in a Comdat!", &GV);
     }
   } else {
     Assert1(GV.hasExternalLinkage() || GV.hasExternalWeakLinkage(),
@@ -578,6 +595,22 @@ void Verifier::visitMDNode(MDNode &MD, Function *F) {
   }
 }
 
+void Verifier::visitComdat(const Comdat &C) {
+  // All Comdat::SelectionKind values other than Comdat::Any require a
+  // GlobalValue with the same name as the Comdat.
+  const GlobalValue *GV = M->getNamedValue(C.getName());
+  if (C.getSelectionKind() != Comdat::Any)
+    Assert1(GV,
+            "comdat selection kind requires a global value with the same name",
+            &C);
+  // The Module is invalid if the GlobalValue has local linkage.  Allowing
+  // otherwise opens us up to seeing the underling global value get renamed if
+  // collisions occur.
+  if (GV)
+    Assert1(!GV->hasLocalLinkage(), "comdat global value has local linkage",
+            GV);
+}
+
 void Verifier::visitModuleIdents(const Module &M) {
   const NamedMDNode *Idents = M.getNamedMetadata("llvm.ident");
   if (!Idents)